etuner: A Redundancy-Aware Framework for Efficient Continual Learning Application on Edge Devices

Many emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and require the deployment of DNN models on edge devices. These applications naturally require i) handling streaming-in inference requests and ii) fine-tuning th...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Li, Sheng, Geng Yuan, Wu, Yawen, Dai, Yue, Wang, Tianyu, Wu, Chao, Jones, Alex K, Hu, Jingtong, Wang, Yanzhi, Tang, Xulong
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 22.08.2024
Subjects
Accuracy
Deep learning
Energy consumption
Inference
Machine learning
Neural networks
Object recognition
Online AccessGet full text

Cover

More Information
Summary:Many emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and require the deployment of DNN models on edge devices. These applications naturally require i) handling streaming-in inference requests and ii) fine-tuning the deployed models to adapt to possible deployment scenario changes. Continual learning (CL) is widely adopted to satisfy these needs. CL is a popular deep learning paradigm that handles both continuous model fine-tuning and overtime inference requests. However, an inappropriate model fine-tuning scheme could involve significant redundancy and consume considerable time and energy, making it challenging to apply CL on edge devices. In this paper, we propose ETuner, an efficient edge continual learning framework that optimizes inference accuracy, fine-tuning execution time, and energy efficiency through both inter-tuning and intra-tuning optimizations. Experimental results show that, on average, ETuner reduces overall fine-tuning execution time by 64%, energy consumption by 56%, and improves average inference accuracy by 1.75% over the immediate model fine-tuning approach.
ISSN:2331-8422